A command for removing logs, file metadata, and other forensic traces from a target system. Forensic traces are records that can help show what happened on a computer.

Use only in an authorized environment for tasks such as a dry-run inventory or approved cleanup of logs and metadata. It supports scopes for logs, metadata, timestamps, or the full set.

It can erase evidence such as login records, system logs, file timestamps, and image or document metadata. Because these actions can destroy records and hide activity, they require careful authorization.

op-clean — Command by ogrodev

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods

npx agentmods add commands/ogrodev/fsociety/op-clean

Clone the repo

git clone --depth 1 https://github.com/ogrodev/fsociety

Per session 12 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 689 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. Scan, not verified.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5	$0.00012	$0.00689
Opus 5	$0.00006	$0.00345
Sonnet 5	$0.00002	$0.00138
Haiku 4.5	$0.00001	$0.00069

Measured 2d ago against content hash abed4c6a55ff, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

op-clean scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

trenton/commands/op-clean.md · 52 lines

What it actually says

Storage Policy: ALL output files MUST be saved in the project directory. NEVER write to /tmp/ or any system temporary directory.

Log and Trace Cleaning

Target and options: $ARGUMENTS

Parse $ARGUMENTS for target host, --scope (default full), and --dry-run flag. Store parsed values for use throughout the command.
If --dry-run is set: enumerate and list all artifacts that would be cleaned for each scope category without executing any destructive operations. Present a summary and exit.
Logs (--scope logs or full): Clear system log entries:
- Truncate or selectively edit /var/log/auth.log, /var/log/syslog, /var/log/kern.log
- Run journalctl --vacuum-time=1s to purge systemd journal entries
- Edit binary login records: wtmp (who was logged in), btmp (failed logins), lastlog (last login per user)
- Clear application-specific logs as identified
Metadata (--scope metadata or full): Strip file metadata from specified paths:
- Use mat2 for broad metadata removal across file types
- Use exiftool -all= for image and document EXIF/XMP data
- Verify metadata removal by re-reading cleaned files
Timestamps (--scope timestamps or full): Manipulate file timestamps to cover tracks:
- Use touch -r <reference-file> <target-file> to copy timestamps from legitimate files
- Use touch -t with specific timestamps to backdate modified files
- Adjust directory timestamps to match surrounding entries
Memory (--scope memory or full): Clear volatile forensic artifacts:
- Clear swap: swapoff -a && swapon -a
- Wipe bash/zsh/python history: truncate ~/.bash_history, ~/.zsh_history, ~/.python_history
- Clear shared memory: remove contents of /dev/shm/
- Drop page cache: echo 3 > /proc/sys/vm/drop_caches
ALWAYS ask the user for explicit confirmation before executing any destructive operations via AskUserQuestion. Show exactly what will be modified or deleted.

Log each cleaning action to the ops tracker with before/after state:

node "${CLAUDE_PLUGIN_ROOT}/scripts/ops-tracker.js" add <target> trace-clean <scope> "<action>" <before-state> <after-state>

Write the cleaning report to the project directory. Include what was cleaned, what was skipped, and any artifacts that could not be removed.

Update session metrics:

node "${CLAUDE_PLUGIN_ROOT}/scripts/session-state.js" metric traces_eliminated

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

2d ago First seen · 52 lines · 12 tokens per session scan A abed4c6a55ff

Subscribe to this mod's changes

op-clean is a command published in the GitHub repository ogrodev/fsociety (20 stars, last pushed 5mo ago), licensed MIT. It adds 12 tokens to every session and 689 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Security claude-code claude-code-plugin offensive-security pentesting

op-clean

Getting it into your agent

What it costs to keep this loaded

Grade A, and why

Nothing flagged

What it actually says

Log and Trace Cleaning

What this file has done since we first saw it

Other commands, from other repositories

review

debug

engage.c2

engage.install

engage.weaponize

engage.deliver